Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িল্লি
    0.37
    ເພ
    0.36
    மாக
    0.36
     fud
    0.35
     <=
    0.34
     Remaining
    0.33
     Ch
    0.32
     quantum
    0.32
     Quantum
    0.32
     ឬ
    0.32
    POSITIVE LOGITS
    ESTER
    0.36
     তৃতীয়
    0.35
    ULU
    0.34
     ಅತ್ಯ
    0.34
     הולנד
    0.34
     NICKEL
    0.34
     கிரேக்க
    0.33
    ándole
    0.32
     "*************
    0.32
    ophilia
    0.32
    Act Density 0.559%

    No Known Activations